mlsanityData to 7 Oct 2026

Learning to Optimize

arXiv 1606.01885 ↗First posted 6 Jun 2016cs.LG cs.AI math.OCcited by 195

Not on the map. Why?

Abstract (arXiv)

Algorithm design is a laborious process and often requires many iterations of ideation and validation. In this paper, we explore automating algorithm design and present a method to learn an optimization algorithm, which we believe to be the first method that can automatically discover a better algorithm. We approach this problem from a reinforcement learning perspective and represent any particular optimization algorithm as a policy. We learn an optimization algorithm using guided policy search and demonstrate that the resulting algorithm outperforms existing hand-engineered algorithms in terms of convergence speed and/or the final objective value.

Key facts. Cited by 195 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Jun 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 48; 2022: 40; 2023: 44; 2024: 31; 2025: 21; 2026: 11.

195 papers.

Sort:

By area:

  1. 2022What Can Transformers Learn In-Context? A Case Study of Simple Function Classescited by 700
  2. 2023Symbolic Discovery of Optimization Algorithmscited by 423
  3. 2021True Few-Shot Learning with Language Modelscited by 343
  4. 2023Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selectioncited by 291
  5. 2023Transformers learn to implement preconditioned gradient descent for in-context learningcited by 274
  6. 2021Learning to Optimize: A Primer and A Benchmarkcited by 206
  7. 2021Trustworthy AI: From Principles to Practicescited by 206
  8. 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 151
  9. 2021Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challengescited by 143
  10. 2022Learning to Learn with Generative Models of Neural Network Checkpointscited by 85
  11. 2022Tutorial on amortized optimizationcited by 83
  12. 2021MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Imagescited by 78
38 more
  1. 2023Permutation Equivariant Neural Functionalscited by 69
  2. 2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
  3. 2021Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyondcited by 62
  4. 2022Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learningcited by 57
  5. 2022VeLO: Training Versatile Learned Optimizers by Scaling Upcited by 57
  6. 2021Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategiescited by 52
  7. 2023Neural Functional Transformerscited by 50
  8. 2021Multi-Objective Meta Learningcited by 39
  9. 2022Transformers are Meta-Reinforcement Learnerscited by 39
  10. 2022Hypernetworks in Meta-Reinforcement Learningcited by 39
  11. 2022Automated Dynamic Algorithm Configurationcited by 37
  12. 2024Diffusion Models as Constrained Samplers for Optimization with Unknown Constraintscited by 33
  13. 2022Practical tradeoffs between memory, compute, and performance in learned optimizerscited by 32
  14. 2022Learning Iterative Reasoning through Energy Minimizationcited by 32
  15. 2023Learning to Warm-Start Fixed-Point Optimization Algorithmscited by 32
  16. 2021A Metalearning Approach for Physics-Informed Neural Networks (PINNs): Application to Parameterized PDEscited by 31
  17. 2021Accelerating Quadratic Optimization with Reinforcement Learningcited by 30
  18. 2022A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biasescited by 30
  19. 2024G3R: Gradient Guided Generalizable Reconstructioncited by 29
  20. 2023A Systematic Review of Few-Shot Learning in Medical Imagingcited by 28
  21. 2021A Bit More Bayesian: Domain-Invariant Learning with Uncertaintycited by 27
  22. 2021How to Train Your MAML to Excel in Few-Shot Classificationcited by 22
  23. 2022Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learningcited by 22
  24. 2021Meta-HAR: Federated Representation Learning for Human Activity Recognitioncited by 21
  25. 2024Position: Leverage Foundational Models for Black-Box Optimizationcited by 21
  26. 2022End-to-End Stochastic Optimization with Energy-Based Modelcited by 19
  27. 2024Offline Model-Based Optimization via Policy-Guided Gradient Searchcited by 19
  28. 2021Out-of-Domain Generalization from a Single Source: An Uncertainty Quantification Approachcited by 18
  29. 2024Verbalized Machine Learning: Revisiting Machine Learning with Language Modelscited by 17
  30. 2022Symbolic Learning to Optimize: Towards Interpretability and Scalabilitycited by 16
  31. 2024In-context Exploration-Exploitation for Reinforcement Learningcited by 16
  32. 2023B2Opt: Learning to Optimize Black-box Optimization with Little Budgetcited by 15
  33. 2024Can Learned Optimization Make Reinforcement Learning Less Difficult?cited by 14
  34. 2021Graph neural network initialisation of quantum approximate optimisationcited by 13
  35. 2021Automated Deep Learning: Neural Architecture Search Is Not the Endcited by 13
  36. 2022Transformer-Based Learned Optimizationcited by 13
  37. 2023Towards Constituting Mathematical Structures for Learning to Optimizecited by 13
  38. 2022A Deep Conjugate Direction Method for Iteratively Solving Linear Systemscited by 12

50 most cited of 195 All 195 (JSON)